Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
SungJoo
/
llama3-8b-instruct-orpo-ko
like
0
Text Generation
Transformers
Safetensors
heegyu/hh-rlhf-ko
Korean
llama
llm
Large Language Model
llama3
ORPO
ORPO β
conversational
text-generation-inference
Inference Endpoints
arxiv:
2403.07691
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
fd4d9bc
llama3-8b-instruct-orpo-ko
/
generation_config.json
SungJoo
Upload LlamaForCausalLM
170f284
verified
8 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"bos_token_id"
:
128000
,
"do_sample"
:
true
,
"eos_token_id"
:
[
128001
,
128009
]
,
"max_length"
:
4096
,
"temperature"
:
0.6
,
"top_p"
:
0.9
,
"transformers_version"
:
"4.38.2"
}